Industrial equipment remote monitoring and maintenance method and system based on big data analysis

Abstract

The invention discloses an industrial equipment remote monitoring maintenance method and system based on big data analysis, and the method comprises the steps: calling industrial equipment data from a historical database, and the industrial equipment data comprises industrial equipment position information and industrial equipment operation data information; according to the invention, the virtual space image information of the operation of the industrial equipment can be displayed based on the digital twin industrial equipment space model, so that workers can remotely and visually know the production efficiency conditions of all industrial equipment in all workshops, and the production efficiency conditions of the industrial equipment are divided into three types; industrial equipment under the three production efficiency conditions of high production efficiency, normal production efficiency and low production efficiency possibly breaks down, different industrial equipment maintenance schemes are formulated according to different production efficiency conditions, the system automatically monitors data and analyzes the data, the number of times of manual on-site troubleshooting and maintenance is reduced, and the production efficiency is improved. And the requirements of workers are met.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment maintenance, and in particular to a method and system for remote monitoring and maintenance of industrial equipment based on big data analysis. Background Art

[0002] As an important part of the Industrial Internet of Things, the health status of industrial equipment is directly related to the quality level of industrial products and the safety of people's lives and property during the production process. Therefore, it is of great theoretical value and engineering practical significance to evaluate the status of industrial equipment to ensure the healthy operation of equipment and prevent accidents.

[0003] The existing industrial equipment maintenance system will monitor the operating data of industrial equipment in real time, and then make judgments based on the experience of the staff, and then conduct inspections and maintenance on the industrial equipment. When there are too many industrial workshops, the number of industrial equipment that needs to be managed is also too large. This method is relatively backward and difficult to meet the needs of the staff. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for optimizing the operating status of industrial production line equipment are provided. The technical solution solves the problem that the existing industrial equipment maintenance system proposed in the above background technology monitors the operating data of industrial equipment in real time, and then makes judgments based on the experience of the staff, and then checks and maintains the industrial equipment. When there are too many industrial workshops, the number of industrial equipment that needs to be managed is also too large. This method is relatively backward.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for remote monitoring and maintenance of industrial equipment based on big data analysis, comprising:

[0007] Retrieving industrial equipment data from a historical database, the industrial equipment data including industrial equipment location information and industrial equipment operation data information, the industrial equipment operation data information including production efficiency information, temperature information and power information of the industrial equipment;

[0008] Based on the layout information of the industrial production line, the location information of the industrial equipment is obtained, and the location information of the industrial equipment and the spatial location of the factory are mapped to build a digital twin industrial equipment space model;

[0009] Collect industrial equipment operation data in real time, integrate the operation data into the digital twin industrial equipment space model, and obtain virtual space image information of industrial equipment;

[0010] Obtain the production efficiency information of all industrial equipment from the virtual space image information of industrial equipment, analyze the production efficiency information data of all industrial equipment, and formulate industrial equipment maintenance plans.

[0011] Preferably, the step of retrieving industrial equipment data from a historical database specifically includes the following steps:

[0012] Obtain a spatial bird's-eye view of each workshop in the factory, and number all workshops in order to obtain the workshop numbers;

[0013] Based on each numbered workshop, count the number and location of industrial equipment in each numbered workshop, number each industrial equipment in each workshop, and obtain the location number of the industrial equipment;

[0014] Cameras and sensors are used to collect production efficiency information, temperature information and power information of each numbered industrial equipment and store them in the database.

[0015] Preferably, the method of collecting production efficiency information, temperature information and power information of each numbered industrial equipment using a camera and a sensor specifically includes the following steps:

[0016] Install intelligent high-definition cameras near industrial equipment to capture the operating status of the industrial equipment in real time and obtain the operating status video of the industrial equipment;

[0017] Analyze the acquired video and determine the number of processed and completed products based on a fixed time period; obtain production efficiency information of industrial equipment based on the fixed time period and the number of processed and completed products;

[0018]

[0019] Where Y V is the production efficiency of industrial equipment, T0 is a fixed time period, and S0 is the number of products processed and completed;

[0020] Sensors are installed on the industrial equipment. The types of the sensors are LM35 sensors and Hall effect sensors. The LM35 sensor is used to collect temperature information of the industrial equipment, and the Hall effect sensor is used to collect power information of the industrial equipment.

[0021] Preferably, the method of obtaining the location information of industrial equipment based on the layout information of the industrial production line, mapping the location information of the industrial equipment and the spatial location of the factory to construct a digital twin industrial equipment spatial model specifically includes the following steps:

[0022] According to the spatial structure of each numbered workshop, construct a three-dimensional model of each numbered workshop;

[0023] According to the location number of each industrial equipment, the position is mapped in the three-dimensional model of each numbered workshop in turn to build a digital twin industrial equipment space model.

[0024] Preferably, the real-time collection of industrial equipment operation data, integration of the operation data in the digital twin industrial equipment space model, and acquisition of industrial equipment virtual space image information specifically include the following steps:

[0025] LM35 sensors and Hall effect sensors collect temperature and power information of various industrial equipment in real time;

[0026] Intelligent high-definition cameras collect real-time data on the production efficiency of various industrial equipment;

[0027] Integrate the temperature information, power information and production efficiency data of each industrial equipment collected in real time into the digital twin industrial equipment space model;

[0028] Import the digital twin industrial equipment space model into the Unity 3D display engine, and integrate the pre-made industrial equipment processing animation effects to obtain the virtual space image information of the industrial equipment.

[0029] Preferably, the step of acquiring the production efficiency information of all industrial equipment from the virtual space image information of the industrial equipment and analyzing the production efficiency information data of all industrial equipment specifically comprises the following steps:

[0030] Comparing the production efficiency data of all industrial equipment with the first preset threshold in sequence;

[0031] If the production efficiency data of the industrial equipment is greater than the first preset threshold, the production efficiency of the industrial equipment is too high;

[0032] If the production efficiency data of the industrial equipment is equal to the first preset threshold, the production efficiency of the industrial equipment is normal;

[0033] If the production efficiency data of the industrial equipment is less than the first preset threshold, the production efficiency of the industrial equipment is too low;

[0034] If the production efficiency data of industrial equipment is zero, the industrial equipment is damaged;

[0035] Conduct fault analysis on damaged industrial equipment and establish an industrial equipment fault analysis model;

[0036] The temperature and power information of industrial equipment with excessive production efficiency, normal production efficiency and low production efficiency are input into the industrial equipment failure analysis model, and the failure probability is obtained.

[0037] Preferably, the industrial equipment failure analysis model is:

[0038]

[0039] In the formula, y=1 represents industrial equipment failure, and y=0 represents industrial equipment normal;

[0040] G is the failure prediction probability of the industrial equipment analysis model;

[0041] M P It is an abnormal operation indicator of the operating power of industrial equipment;

[0042] M T It is an abnormal operating indicator of the operating temperature of industrial equipment;

[0043] b, b, and c are coefficients of the industrial equipment failure analysis model;

[0044] The calculation formula of the abnormal operation index is:

[0045] M=∑Δ 偏 ×t

[0046] In the formula, Δ 偏 is the offset of the running data relative to the standard running data,

[0047] t is the industrial equipment in Δ 偏 The running time in the state;

[0048] The calculation method of a, b and c is:

[0049] Classify the historical operation data according to whether the industrial equipment eventually fails, and obtain several groups of historical operation data of industrial equipment that eventually fails and several groups of historical operation data of industrial equipment that eventually does not fail;

[0050] According to the historical operation data of several groups of industrial equipment that eventually fail and the historical operation data of several groups of industrial equipment that eventually do not fail, α, β1 and β2 are calculated by the maximum likelihood method;

[0051] Test the significance of α, β1 and β2 on the parameters of the fault risk prediction model, and determine whether α, β1 and β2 meet the significance requirements.

[0052] Preferably, the temperature information and power information of industrial equipment with excessive production efficiency, normal production efficiency and low production efficiency, and the real-time temperature information and power information are input into the industrial equipment fault analysis model to obtain the fault probability, specifically comprising the following steps:

[0053] Inputting temperature information and power information of industrial equipment with excessive production efficiency, normal production efficiency, and low production efficiency into an industrial equipment fault analysis model to obtain a first fault prediction value, a second fault prediction value, and a third fault prediction value;

[0054] Comparing the first fault prediction value, the second fault prediction value, and the third fault prediction value with the second preset threshold value in sequence;

[0055] If the first fault prediction value and the second fault prediction value are greater than or equal to the second preset threshold, the over-production efficiency and normal production efficiency fault rates are relatively high, and the location information of the industrial equipment in these two states is obtained from the digital twin industrial equipment space model for maintenance;

[0056] If the first fault prediction value and the second fault prediction value are less than the second preset threshold value, the industrial equipment with normal production efficiency has no fault, and a secondary fault analysis is performed on the industrial equipment with excessive production efficiency;

[0057] If the third fault prediction value is greater than or equal to the second preset threshold, the failure rate of the industrial equipment with too low production efficiency is relatively high, and the location information of the industrial equipment in this state is obtained from the digital twin industrial equipment space model for maintenance;

[0058] If the third fault prediction value is less than the second preset threshold, the industrial equipment has too low production efficiency, and the maintenance time interval of the industrial equipment in the state of too low production efficiency is analyzed.

[0059] Preferably, the analysis of the maintenance time interval of industrial equipment in a state of too low production efficiency specifically includes the following steps:

[0060] Get the time of the last maintenance operation of industrial equipment with low production efficiency;

[0061] Obtain the time point when the production efficiency of industrial equipment is too low;

[0062] Obtain maintenance time intervals for industrial equipment based on two time points;

[0063] T=T2-T1

[0064] In the formula, T is the maintenance time interval, T2 is the time point when the industrial equipment has low production efficiency, and T1 is the time point when the industrial equipment was last maintained.

[0065] comparing the obtained maintenance time interval of the industrial equipment with a third preset threshold;

[0066] If the maintenance time interval of the industrial equipment is greater than or equal to a third preset threshold, reminding the staff to perform maintenance;

[0067] If the maintenance time interval of the industrial equipment is less than a third preset threshold, a secondary fault analysis is performed;

[0068] The performing of secondary fault analysis on industrial equipment whose production efficiency is less than the second preset threshold and is too high and the performing of secondary fault analysis on industrial equipment whose maintenance time interval is less than the third preset threshold and whose production efficiency is too low specifically comprises the following steps:

[0069] Collect the production efficiency of all industrial equipment in a historical day under the conditions that the production efficiency is less than a second preset threshold and is too high, and the maintenance time interval is less than a third preset threshold and the production efficiency is too low, wherein the production efficiency conditions include too high, normal, and too low;

[0070] Count the number of times that the value is too high, normal, and too low, and sum them up to obtain the total number of times that the value is too high, the total number of times that the value is normal, and the total number of times that the value is too low;

[0071] Sum up the total number of times of being too strong and the total number of times of being too low again to obtain the total number of abnormalities;

[0072] Comparing the total number of abnormalities with a fourth preset threshold;

[0073] If the total number of abnormalities is greater than or equal to a fourth preset threshold, obtain the location information of the industrial equipment for secondary fault analysis from the digital twin industrial equipment spatial model and perform maintenance;

[0074] If the total number of abnormalities is less than the fourth preset threshold, the industrial equipment is normal.

[0075] A remote monitoring and maintenance system for industrial equipment based on big data analysis, comprising:

[0076] A retrieval module, the retrieval module is used to retrieve industrial equipment data from a historical database;

[0077] A model building module, wherein the model building module is used to obtain the location information of industrial equipment based on the layout information of the industrial production line, and to construct a digital twin industrial equipment spatial model by mapping the industrial equipment location information and the spatial location of the factory;

[0078] A spatial image construction module, which is used to collect industrial equipment operation data in real time, fuse the operation data in the digital twin industrial equipment spatial model, and obtain virtual spatial image information of the industrial equipment;

[0079] The maintenance plan module is used to obtain the production efficiency information of all industrial equipment from the virtual space image information of the industrial equipment, analyze the production efficiency information data of all industrial equipment, and formulate a maintenance plan for the industrial equipment.

[0080] Compared with the prior art, the present invention provides a method and system for remote monitoring and maintenance of industrial equipment based on big data analysis, which has the following beneficial effects:

[0081] The present invention can display virtual space image information of industrial equipment operation based on the digital twin industrial equipment space model, so that the staff can remotely and intuitively understand the production efficiency of all industrial equipment in all workshops. The production efficiency of industrial equipment is divided into three types: excessive production efficiency, normal production efficiency and too low production efficiency. Industrial equipment in these three production efficiency conditions are likely to fail, and different industrial equipment maintenance plans are formulated for different production efficiency conditions. Among them, the industrial equipment with too low production efficiency whose third fault prediction value is less than the second preset threshold may be interfered by the maintenance time interval factor. The industrial equipment in this state is further checked. The system automatically monitors and analyzes the data, reduces the number of manual on-site inspections and maintenance, and meets the needs of the staff. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Figure 1 A schematic diagram of the industrial equipment remote monitoring and maintenance method of the present invention;

[0083] Figure 2 A schematic diagram of a method for retrieving industrial equipment data from a historical database in the present invention;

[0084] Figure 3 A schematic diagram of a method for collecting production efficiency information, temperature information and power information in the present invention;

[0085] Figure 4 A schematic diagram of a method for constructing a digital twin industrial equipment spatial model in the present invention;

[0086] Figure 5 A schematic diagram of a method for obtaining virtual space image information of industrial equipment in the present invention;

[0087] Figure 6 It is a schematic diagram of a method for analyzing production efficiency information data in the present invention;

[0088] Figure 7 It is a schematic diagram of the method for obtaining the failure probability in the present invention. DETAILED DESCRIPTION

[0089] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0090] Example 1

[0091] Please refer to Figure 1-Figure 7 As shown, a remote monitoring and maintenance method for industrial equipment based on big data analysis includes:

[0092] Retrieving industrial equipment data from a historical database, the industrial equipment data including industrial equipment location information and industrial equipment operation data information, the industrial equipment operation data information including production efficiency information, temperature information and power information of the industrial equipment;

[0093] Based on the layout information of the industrial production line, the location information of the industrial equipment is obtained, and the location information of the industrial equipment and the spatial location of the factory are mapped to build a digital twin industrial equipment space model;

[0094] Collect industrial equipment operation data in real time, integrate the operation data into the digital twin industrial equipment space model, and obtain virtual space image information of industrial equipment;

[0095] Obtain the production efficiency information of all industrial equipment from the virtual space image information of industrial equipment, analyze the production efficiency information data of all industrial equipment, and formulate industrial equipment maintenance plans.

[0096] People in this technical field can understand that the present invention can display virtual space image information of industrial equipment operation based on the digital twin industrial equipment space model, so that staff can remotely and intuitively understand the production efficiency of all industrial equipment in all workshops. The production efficiency of industrial equipment is divided into three types: excessive production efficiency, normal production efficiency and too low production efficiency. Industrial equipment in these three production efficiency conditions are likely to fail, and different industrial equipment maintenance plans are formulated for different production efficiency conditions. Among them, industrial equipment with too low production efficiency whose third fault prediction value is less than the second preset threshold may be interfered by maintenance time interval factors. Further inspection of industrial equipment in this state is carried out. The system automatically monitors and analyzes data, reduces the number of manual on-site inspections and maintenance, and meets the needs of staff.

[0097] Retrieving industrial equipment data from the historical database specifically includes the following steps:

[0098] Obtain a spatial bird's-eye view of each workshop in the factory, and number all workshops in order to obtain the workshop numbers;

[0099] Based on each numbered workshop, count the number and location of industrial equipment in each numbered workshop, number each industrial equipment in each workshop, and obtain the location number of the industrial equipment;

[0100] Cameras and sensors are used to collect production efficiency information, temperature information and power information of each numbered industrial equipment and store them in the database.

[0101] The specific steps of using cameras and sensors to collect production efficiency information, temperature information and power information of each numbered industrial equipment are as follows:

[0102] Install intelligent high-definition cameras near industrial equipment to capture the operating status of the industrial equipment in real time and obtain the operating status video of the industrial equipment;

[0103] Analyze the acquired videos and determine the number of products processed and completed based on a fixed time period;

[0104] Obtain information on the production efficiency of industrial equipment based on a fixed time period and the number of products processed and completed;

[0105]

[0106] Where Y V is the production efficiency of industrial equipment, T0 is a fixed time period, and S0 is the number of products processed and completed;

[0107] Sensors are installed on the industrial equipment. The types of sensors are LM35 sensors and Hall effect sensors. The LM35 sensor is used to collect temperature information of the industrial equipment, and the Hall effect sensor is used to collect power information of the industrial equipment.

[0108] Based on the layout information of the industrial production line, the location information of the industrial equipment is obtained, and the location information of the industrial equipment and the spatial location of the factory are mapped to construct a digital twin industrial equipment spatial model, which specifically includes the following steps:

[0109] According to the spatial structure of each numbered workshop, construct a three-dimensional model of each numbered workshop;

[0110] According to the location number of each industrial equipment, the position is mapped in the three-dimensional model of each numbered workshop in turn to build a digital twin industrial equipment space model.

[0111] Real-time collection of industrial equipment operation data, integration of operation data in the digital twin industrial equipment space model, and acquisition of industrial equipment virtual space image information specifically include the following steps:

[0112] LM35 sensors and Hall effect sensors collect temperature and power information of various industrial equipment in real time;

[0113] Intelligent high-definition cameras collect real-time data on the production efficiency of various industrial equipment;

[0114] Integrate the temperature information, power information and production efficiency data of each industrial equipment collected in real time into the digital twin industrial equipment space model;

[0115] Import the digital twin industrial equipment space model into the Unity 3D display engine, and integrate the pre-made industrial equipment processing animation effects to obtain the virtual space image information of the industrial equipment.

[0116] The production efficiency information of all industrial equipment is obtained from the virtual space image information of the industrial equipment, and the production efficiency information data of all industrial equipment is analyzed, which specifically includes the following steps:

[0117] Comparing the production efficiency data of all industrial equipment with the first preset threshold in sequence;

[0118] If the production efficiency data of the industrial equipment is greater than the first preset threshold, the production efficiency of the industrial equipment is too high;

[0119] If the production efficiency data of the industrial equipment is equal to the first preset threshold, the production efficiency of the industrial equipment is normal;

[0120] If the production efficiency data of the industrial equipment is less than the first preset threshold, the production efficiency of the industrial equipment is too low;

[0121] If the production efficiency data of industrial equipment is zero, the industrial equipment is damaged;

[0122] Conduct fault analysis on damaged industrial equipment and establish an industrial equipment fault analysis model;

[0123] The temperature and power information of industrial equipment with excessive production efficiency, normal production efficiency and low production efficiency are input into the industrial equipment failure analysis model, and the failure probability is obtained.

[0124] The industrial equipment failure analysis model is:

[0125]

[0126] In the formula, y=1 represents industrial equipment failure, and y=0 represents industrial equipment normal;

[0127] G is the failure prediction probability of the industrial equipment analysis model;

[0128] M P It is an abnormal operation indicator of the operating power of industrial equipment;

[0129] M T It is an abnormal operating indicator of the operating temperature of industrial equipment;

[0130] c, b, and c are all coefficients of the industrial equipment failure analysis model;

[0131] The calculation formula of abnormal operation index is:

[0132] M=∑Δ 偏 ×t

[0133] In the formula, Δ 偏 is the offset of the running data relative to the standard running data,

[0134] t is the industrial equipment in Δ 偏 The running time in the state;

[0135] The calculation method of a, b and c is:

[0136] Classify the historical operation data according to whether the industrial equipment eventually fails, and obtain several groups of historical operation data of industrial equipment that eventually fails and several groups of historical operation data of industrial equipment that eventually does not fail;

[0137] According to the historical operation data of several groups of industrial equipment that eventually fail and the historical operation data of several groups of industrial equipment that eventually do not fail, α, β1 and β2 are calculated by the maximum likelihood method;

[0138] Test the significance of α, β1 and β2 on the parameters of the fault risk prediction model, and determine whether α, β1 and β2 meet the significance requirements.

[0139] The temperature information and power information of industrial equipment with excessive production efficiency, normal production efficiency and low production efficiency are input into the industrial equipment fault analysis model, and the specific steps of obtaining the fault probability are as follows:

[0140] Inputting temperature information and power information of industrial equipment with excessive production efficiency, normal production efficiency, and low production efficiency into an industrial equipment fault analysis model to obtain a first fault prediction value, a second fault prediction value, and a third fault prediction value;

[0141] Comparing the first fault prediction value, the second fault prediction value, and the third fault prediction value with the second preset threshold value in sequence;

[0142] If the first fault prediction value and the second fault prediction value are greater than or equal to the second preset threshold, the over-production efficiency and normal production efficiency fault rates are relatively high, and the location information of the industrial equipment in these two states is obtained from the digital twin industrial equipment space model for maintenance;

[0143] If the first fault prediction value and the second fault prediction value are less than the second preset threshold value, the industrial equipment with normal production efficiency has no fault, and a secondary fault analysis is performed on the industrial equipment with excessive production efficiency;

[0144] If the third fault prediction value is greater than or equal to the second preset threshold, the failure rate of the industrial equipment with too low production efficiency is relatively high, and the location information of the industrial equipment in this state is obtained from the digital twin industrial equipment space model for maintenance;

[0145] If the third fault prediction value is less than the second preset threshold, the industrial equipment has too low production efficiency, and the maintenance time interval of the industrial equipment in the state of too low production efficiency is analyzed.

[0146] The analysis of the maintenance intervals for industrial equipment that is in a state of low production efficiency includes the following steps:

[0147] Get the time of the last maintenance operation of industrial equipment with low production efficiency;

[0148] Obtain the time point when the production efficiency of industrial equipment is too low;

[0149] Obtain maintenance time intervals for industrial equipment based on two time points;

[0150] T=T2-T1

[0151] In the formula, T is the maintenance time interval, T2 is the time point when the industrial equipment has low production efficiency, and T1 is the time point when the industrial equipment was last maintained.

[0152] comparing the obtained maintenance time interval of the industrial equipment with a third preset threshold;

[0153] If the maintenance time interval of the industrial equipment is greater than or equal to a third preset threshold, reminding the staff to perform maintenance;

[0154] If the maintenance time interval of the industrial equipment is less than a third preset threshold, a secondary fault analysis is performed;

[0155] The secondary fault analysis of industrial equipment whose production efficiency is less than the second preset threshold and is too high and the secondary fault analysis of industrial equipment whose maintenance time interval is less than the third preset threshold and whose production efficiency is too low specifically includes the following steps:

[0156] Collect the production efficiency of all industrial equipment in a historical day under the conditions that the production efficiency is less than the second preset threshold and is too high, and the maintenance time interval is less than the third preset threshold and the production efficiency is too low, and the production efficiency conditions include excessive, normal and too low;

[0157] Count the number of times that the value is too high, normal, and too low, and sum them up to obtain the total number of times that the value is too high, the total number of times that the value is normal, and the total number of times that the value is too low;

[0158] Sum up the total number of times of being too strong and the total number of times of being too low again to obtain the total number of abnormalities;

[0159] Comparing the total number of abnormalities with a fourth preset threshold;

[0160] If the total number of abnormalities is greater than or equal to a fourth preset threshold, obtain the location information of the industrial equipment for secondary fault analysis from the digital twin industrial equipment spatial model and perform maintenance;

[0161] If the total number of abnormalities is less than the fourth preset threshold, the industrial equipment is normal.

[0162] A remote monitoring and maintenance system for industrial equipment based on big data analysis, comprising:

[0163] A retrieval module, which is used to retrieve industrial equipment data from a historical database;

[0164] Model building module: The model building module is used to obtain the location information of industrial equipment based on the layout information of the industrial production line, and to build a digital twin industrial equipment spatial model by mapping the industrial equipment location information and the spatial location of the factory;

[0165] The spatial image construction module is used to collect the operation data of industrial equipment in real time, integrate the operation data into the digital twin industrial equipment spatial model, and obtain the virtual spatial image information of industrial equipment;

[0166] The maintenance plan module is used to obtain the production efficiency information of all industrial equipment from the virtual space image information of industrial equipment, analyze the production efficiency information data of all industrial equipment, and formulate industrial equipment maintenance plans.

[0167] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A remote monitoring and maintenance method for industrial equipment based on big data analysis, characterized in that: include: Retrieving industrial equipment data from a historical database, the industrial equipment data including industrial equipment location information and industrial equipment operation data information, the industrial equipment operation data information including production efficiency information, temperature information and power information of the industrial equipment; Based on the layout information of the industrial production line, the location information of the industrial equipment is obtained, and the location information of the industrial equipment and the spatial location of the factory are mapped to build a digital twin industrial equipment space model; Collect industrial equipment operation data in real time, integrate the operation data into the digital twin industrial equipment space model, and obtain virtual space image information of industrial equipment; Obtain the production efficiency information of all industrial equipment from the virtual space image information of industrial equipment, analyze the production efficiency information data of all industrial equipment, and formulate industrial equipment maintenance plans.

2. According to claim 1, a method for remote monitoring and maintenance of industrial equipment based on big data analysis is characterized in that: The method of retrieving industrial equipment data from the historical database specifically includes the following steps: Obtain a spatial bird's-eye view of each workshop in the factory, and number all workshops in order to obtain the workshop numbers; Based on each numbered workshop, count the number and location of industrial equipment in each numbered workshop, number each industrial equipment in each workshop, and obtain the location number of the industrial equipment; Cameras and sensors are used to collect production efficiency information, temperature information and power information of each numbered industrial equipment and store them in the database.

3. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 2 is characterized in that: The method of using cameras and sensors to collect production efficiency information, temperature information and power information of each numbered industrial equipment specifically includes the following steps: Install intelligent high-definition cameras near industrial equipment to capture the operating status of the industrial equipment in real time and obtain the operating status video of the industrial equipment; Analyze the acquired videos and determine the number of products processed and completed based on a fixed time period; Obtain information on the production efficiency of industrial equipment based on a fixed time period and the number of products processed and completed; Where Y V is the production efficiency of industrial equipment, T0 is a fixed time period, and S0 is the number of products processed and completed; Sensors are installed on the industrial equipment. The types of the sensors are LM35 sensors and Hall effect sensors. The LM35 sensor is used to collect temperature information of the industrial equipment, and the Hall effect sensor is used to collect power information of the industrial equipment.

4. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 3 is characterized in that: The method of obtaining the location information of industrial equipment based on the layout information of the industrial production line, mapping the location information of the industrial equipment and the spatial location of the factory to construct a digital twin industrial equipment spatial model specifically includes the following steps: According to the spatial structure of each numbered workshop, construct a three-dimensional model of each numbered workshop; According to the location number of each industrial equipment, the position is mapped in the three-dimensional model of each numbered workshop in turn to build a digital twin industrial equipment space model.

5. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 4 is characterized in that: The real-time collection of industrial equipment operation data, integration of the operation data in the digital twin industrial equipment space model, and acquisition of industrial equipment virtual space image information specifically include the following steps: LM35 sensors and Hall effect sensors collect temperature and power information of various industrial equipment in real time; Intelligent high-definition cameras collect real-time data on the production efficiency of various industrial equipment; Integrate the temperature information, power information and production efficiency data of each industrial equipment collected in real time into the digital twin industrial equipment space model; Import the digital twin industrial equipment space model into the Unity 3D display engine, and integrate the pre-made industrial equipment processing animation effects to obtain the virtual space image information of the industrial equipment.

6. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 5 is characterized in that: The step of obtaining the production efficiency information of all industrial equipment from the virtual space image information of the industrial equipment and analyzing the production efficiency information data of all industrial equipment specifically includes the following steps: Comparing the production efficiency data of all industrial equipment with the first preset threshold in sequence; If the production efficiency data of the industrial equipment is greater than the first preset threshold, the production efficiency of the industrial equipment is too high; If the production efficiency data of the industrial equipment is equal to the first preset threshold, the production efficiency of the industrial equipment is normal; If the production efficiency data of the industrial equipment is less than the first preset threshold, the production efficiency of the industrial equipment is too low; If the production efficiency data of industrial equipment is zero, the industrial equipment is damaged; Conduct fault analysis on damaged industrial equipment and establish an industrial equipment fault analysis model; The temperature and power information of industrial equipment with excessive production efficiency, normal production efficiency and low production efficiency are input into the industrial equipment failure analysis model, and the failure probability is obtained.

7. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 6 is characterized in that: The industrial equipment failure analysis model is: In the formula, y=1 represents industrial equipment failure, and y=0 represents industrial equipment normal; G is the failure prediction probability of the industrial equipment analysis model; M P It is an abnormal operation indicator of the operating power of industrial equipment; M T It is an abnormal operating indicator of the operating temperature of industrial equipment; a, b, and c are coefficients of the industrial equipment failure analysis model; The calculation formula of the abnormal operation index is: M=∑Δ 偏 ×t In the formula, Δ 偏 is the offset of the running data relative to the standard running data, t is the industrial equipment in Δ 偏 The running time in the state; The calculation method of a, b and c is: Classify the historical operation data according to whether the industrial equipment eventually fails, and obtain several groups of historical operation data of industrial equipment that eventually fails and several groups of historical operation data of industrial equipment that eventually does not fail; According to the historical operation data of several groups of industrial equipment that eventually fail and the historical operation data of several groups of industrial equipment that eventually do not fail, α, β1 and β2 are calculated by the maximum likelihood method; Test the significance of α, β1 and β2 on the parameters of the fault risk prediction model, and determine whether α, β1 and β2 meet the significance requirements.

8. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 7 is characterized in that: The temperature information and power information of industrial equipment with excessive production efficiency, normal production efficiency and low production efficiency, and the real-time temperature information and power information are input into the industrial equipment fault analysis model to obtain the fault probability, specifically including the following steps: Inputting temperature information and power information of industrial equipment with excessive production efficiency, normal production efficiency, and low production efficiency into an industrial equipment fault analysis model to obtain a first fault prediction value, a second fault prediction value, and a third fault prediction value; Comparing the first fault prediction value, the second fault prediction value, and the third fault prediction value with the second preset threshold value in sequence; If the first fault prediction value and the second fault prediction value are greater than or equal to the second preset threshold, the over-production efficiency and normal production efficiency fault rates are relatively high, and the location information of the industrial equipment in these two states is obtained from the digital twin industrial equipment space model for maintenance; If the first fault prediction value and the second fault prediction value are less than the second preset threshold value, the industrial equipment with normal production efficiency has no fault, and a secondary fault analysis is performed on the industrial equipment with excessive production efficiency; If the third fault prediction value is greater than or equal to the second preset threshold, the failure rate of the industrial equipment with too low production efficiency is relatively high, and the location information of the industrial equipment in this state is obtained from the digital twin industrial equipment space model for maintenance; If the third fault prediction value is less than the second preset threshold, the industrial equipment has too low production efficiency, and the maintenance time interval of the industrial equipment in the state of too low production efficiency is analyzed.

9. The method for remote monitoring and maintenance of industrial equipment based on big data analysis according to claim 8, characterized in that: The analysis of the maintenance time interval of industrial equipment in a state of too low production efficiency specifically includes the following steps: Get the time of the last maintenance operation of industrial equipment with low production efficiency; Obtain the time point when the production efficiency of industrial equipment is too low; Obtain maintenance intervals for industrial equipment based on two time points; T=T2-T1 In the formula, T is the maintenance time interval, T2 is the time point when the industrial equipment has low production efficiency, and T1 is the time point when the industrial equipment was last maintained. comparing the obtained maintenance time interval of the industrial equipment with a third preset threshold; If the maintenance time interval of the industrial equipment is greater than or equal to a third preset threshold, reminding the staff to perform maintenance; If the maintenance time interval of the industrial equipment is less than a third preset threshold, a secondary fault analysis is performed; The performing of secondary fault analysis on industrial equipment whose production efficiency is less than the second preset threshold and is too high and the performing of secondary fault analysis on industrial equipment whose maintenance time interval is less than the third preset threshold and whose production efficiency is too low specifically comprises the following steps: Collect the production efficiency of all industrial equipment in a historical day under the conditions that the production efficiency is less than a second preset threshold and is too high, and the maintenance time interval is less than a third preset threshold and the production efficiency is too low, wherein the production efficiency conditions include too high, normal, and too low; Count the number of times that the value is too high, normal, and too low, and sum them up to obtain the total number of times that the value is too high, the total number of times that the value is normal, and the total number of times that the value is too low; Sum up the total number of times of being too strong and the total number of times of being too low again to obtain the total number of abnormalities; Comparing the total number of abnormalities with a fourth preset threshold; If the total number of abnormalities is greater than or equal to a fourth preset threshold, obtain the location information of the industrial equipment for secondary fault analysis from the digital twin industrial equipment spatial model and perform maintenance; If the total number of abnormalities is less than the fourth preset threshold, the industrial equipment is normal.

10. A remote monitoring and maintenance system for industrial equipment based on big data analysis, used to implement a remote monitoring and maintenance method for industrial equipment based on big data analysis as described in any one of claims 1 to 9, characterized in that: include: A retrieval module, the retrieval module is used to retrieve industrial equipment data from a historical database; A model building module, wherein the model building module is used to obtain the location information of industrial equipment based on the layout information of the industrial production line, and to construct a digital twin industrial equipment spatial model by mapping the industrial equipment location information and the spatial location of the factory; A spatial image construction module, which is used to collect industrial equipment operation data in real time, fuse the operation data in the digital twin industrial equipment spatial model, and obtain virtual spatial image information of the industrial equipment; The maintenance plan module is used to obtain the production efficiency information of all industrial equipment from the virtual space image information of the industrial equipment, analyze the production efficiency information data of all industrial equipment, and formulate a maintenance plan for the industrial equipment.

Images